[Router] Add bucket-aware policy domains and native cache indexing (#38108)

Signed-off-by: Vincent Gao <vincentbo@linux.alibaba.com>
Co-authored-by: inkcherry <mingzhi.liu@amd.com>
Co-authored-by: yangbodong22011 <13137470+yangbodong22011@users.noreply.github.com>

experimental/sgl-router/monitoring/grafana-dashboard.json

@@ -1605,111 +1605,6 @@
         }
       ]
     },
-    {
-      "type": "timeseries",
-      "title": "Overlap blocks quantiles",
-      "description": "Cache-aware-zmq overlap-block count at policy selection.",
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${datasource}"
-      },
-      "gridPos": {
-        "x": 16,
-        "y": 41,
-        "w": 8,
-        "h": 8
-      },
-      "id": 23,
-      "fieldConfig": {
-        "defaults": {
-          "unit": "short",
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "drawStyle": "line",
-            "fillOpacity": 0,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "never",
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green",
-                "value": null
-              }
-            ]
-          }
-        },
-        "overrides": []
-      },
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "bottom",
-          "showLegend": true
-        },
-        "tooltip": {
-          "mode": "multi",
-          "sort": "desc"
-        }
-      },
-      "pluginVersion": "11.6.0",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${datasource}"
-          },
-          "editorMode": "code",
-          "expr": "histogram_quantile(0.5, sum by (le) (rate(sgl_router_overlap_blocks_bucket{model_id=~\"$model_id\"}[$__rate_interval])))",
-          "range": true,
-          "refId": "A",
-          "legendFormat": "p50",
-          "format": "time_series"
-        },
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${datasource}"
-          },
-          "editorMode": "code",
-          "expr": "histogram_quantile(0.99, sum by (le) (rate(sgl_router_overlap_blocks_bucket{model_id=~\"$model_id\"}[$__rate_interval])))",
-          "range": true,
-          "refId": "B",
-          "legendFormat": "p99",
-          "format": "time_series"
-        }
-      ]
-    },
     {
       "type": "row",
       "title": "Routing Policy",